Tsubasa Ochiai

108 papers A* 2A 22Misc 26Journal 51Unranked 7

Year	Rank	Type	Title / Venue / Authors
2026	J	`jnl`	Frontend Token Enhancement for Token-Based Speech Recognition. CoRR Takanori Ashihara, Shota Horiguchi, Kohei Matsuura, Tsubasa Ochiai, Marc Delcroix
2026	J	`jnl`	Microphone array geometry-independent multi-talker distant ASR: NTT system for DASR task of the CHiME-8 challenge. Comput. Speech Lang. Naoyuki Kamo, Naohiro Tawara, Atsushi Ando, Takatomo Kano, Hiroshi Sato, Rintaro Ikeshita, Takafumi Moriya, Shota Horiguchi, Kohei Matsuura, Atsunori Ogawa, Alexis Plaquet, Takanori Ashihara, Tsubasa Ochiai, Masato Mimura, Marc Delcroix, Tomohiro Nakatani, Taichi Asami, Shoko Araki
2025	A	`conf`	Analysis of Semantic and Acoustic Token Variability Across Speech, Music, and Audio Domains. INTERSPEECH Takanori Ashihara, Marc Delcroix, Tsubasa Ochiai, Kohei Matsuura, Shota Horiguchi
2025	J	`jnl`	Generic Speech Enhancement with Self-Supervised Representation Space Loss. CoRR Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Ryo Masumura
2025	A	`conf`	MOVER: Combining Multiple Meeting Recognition Systems. INTERSPEECH Naoyuki Kamo, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani
2025	J	`jnl`	Microphone Array Signal Processing and Deep Learning for Speech Enhancement. CoRR Reinhold Haeb-Umbach, Tomohiro Nakatani, Marc Delcroix, Christoph Boeddeker, Tsubasa Ochiai
2025	A	`conf`	Real-time TSE demonstration via SoundBeam with KD. INTERSPEECH Keigo Wakayama, Tomoko Kawase, Takafumi Moriya, Marc Delcroix, Hiroshi Sato, Tsubasa Ochiai, Masahiro Yasuda, Shoko Araki
2025	Misc	`conf`	SoundBeam meets M2D: Target Sound Extraction with Audio Foundation Model. ICASSP Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai, Daisuke Niizumi, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki
2025	Misc	`conf`	TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models. ICASSP Junyi Peng, Takanori Ashihara, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki, Jan Cernocký
2025	J	`jnl`	TS-SUPERB: A Target Speech Processing Benchmark for Speech Self-Supervised Learning Models. CoRR Junyi Peng, Takanori Ashihara, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki, Jan Cernocký
2024	A	`conf`	Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers. INTERSPEECH Marvin Tammen, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Shoko Araki, Simon Doclo
2024	J	`jnl`	Array Geometry-Robust Attention-Based Neural Beamformer for Moving Speakers. CoRR Marvin Tammen, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Shoko Araki, Simon Doclo
2024	Misc	`conf`	How Does End-To-End Speech Recognition Training Impact Speech Enhancement Artifacts? ICASSP Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2024	—	`conf`	Interaural Time Difference Loss for Binaural Target Sound Extraction. IWAENC Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki
2024	J	`jnl`	Interaural time difference loss for binaural target sound extraction. CoRR Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki
2024	—	`conf`	Investigation of Speaker Representation for Target-Speaker Speech Processing. SLT Takanori Ashihara, Takafumi Moriya, Shota Horiguchi, Junyi Peng, Tsubasa Ochiai, Marc Delcroix, Kohei Matsuura, Hiroshi Sato
2024	J	`jnl`	Investigation of Speaker Representation for Target-Speaker Speech Processing. CoRR Takanori Ashihara, Takafumi Moriya, Shota Horiguchi, Junyi Peng, Tsubasa Ochiai, Marc Delcroix, Kohei Matsuura, Hiroshi Sato
2024	J	`jnl`	Microphone Array Signal Processing and Deep Learning for Speech Enhancement: Combining model-based and data-driven approaches to parameter estimation and filtering [Special Issue On Model-Based and Data-Driven Audio Signal Processing]. IEEE Signal Process. Mag. Reinhold Häb-Umbach, Tomohiro Nakatani, Marc Delcroix, Christoph Boeddeker, Tsubasa Ochiai
2024	J	`jnl`	Module-Based End-to-End Distant Speech Processing: A case study of far-field automatic speech recognition [Special Issue On Model-Based and Data-Driven Audio Signal Processing]. IEEE Signal Process. Mag. Xuankai Chang, Shinji Watanabe, Marc Delcroix, Tsubasa Ochiai, Wangyou Zhang, Yanmin Qian
2024	Misc	`conf`	Neural Network-Based Virtual Microphone Estimation with Virtual Microphone and Beamformer-Level Multi-Task Loss. ICASSP Hanako Segawa, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Shoko Araki, Takeshi Yamada, Shoji Makino
2024	Misc	`conf`	Online Target Sound Extraction with Knowledge Distillation from Partially Non-Causal Teacher. ICASSP Keigo Wakayama, Tsubasa Ochiai, Marc Delcroix, Masahiro Yasuda, Shoichiro Saito, Shoko Araki, Akira Nakayama
2024	—	`conf`	Probing Self-Supervised Learning Models With Target Speech Extraction. ICASSP Workshops Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Takanori Ashihara, Shoko Araki, Jan Cernocký
2024	J	`jnl`	Probing Self-supervised Learning Models with Target Speech Extraction. CoRR Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Takanori Ashihara, Shoko Araki, Jan Cernocký
2024	J	`jnl`	Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance. CoRR Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2024	J	`jnl`	Rethinking Processing Distortions: Disentangling the Impact of Speech Enhancement Errors on Speech Recognition Performance. IEEE ACM Trans. Audio Speech Lang. Process. Tsubasa Ochiai, Kazuma Iwamoto, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2024	J	`jnl`	SoundBeam meets M2D: Target Sound Extraction with Audio Foundation Model. CoRR Carlos Hernandez-Olivan, Marc Delcroix, Tsubasa Ochiai, Daisuke Niizumi, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki
2024	A	`conf`	SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling. INTERSPEECH Hiroshi Sato, Takafumi Moriya, Masato Mimura, Shota Horiguchi, Tsubasa Ochiai, Takanori Ashihara, Atsushi Ando, Kentaro Shinayama, Marc Delcroix
2024	J	`jnl`	SpeakerBeam-SS: Real-time Target Speaker Extraction with Lightweight Conv-TasNet and State Space Modeling. CoRR Hiroshi Sato, Takafumi Moriya, Masato Mimura, Shota Horiguchi, Tsubasa Ochiai, Takanori Ashihara, Atsushi Ando, Kentaro Shinayama, Marc Delcroix
2024	Misc	`conf`	Target Speech Extraction with Pre-Trained Self-Supervised Learning Models. ICASSP Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki, Jan Cernocký
2024	J	`jnl`	Target Speech Extraction with Pre-trained Self-supervised Learning Models. CoRR Junyi Peng, Marc Delcroix, Tsubasa Ochiai, Oldrich Plchot, Shoko Araki, Jan Cernocký
2023	A	`conf`	Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss. INTERSPEECH Hiroshi Sato, Ryo Masumura, Tsubasa Ochiai, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Kentaro Shinayama, Saki Mizuno, Mana Ihori, Tomohiro Tanaka, Nobukatsu Hojo
2023	J	`jnl`	Downstream Task Agnostic Speech Enhancement with Self-Supervised Representation Loss. CoRR Hiroshi Sato, Ryo Masumura, Tsubasa Ochiai, Marc Delcroix, Takafumi Moriya, Takanori Ashihara, Kentaro Shinayama, Saki Mizuno, Mana Ihori, Tomohiro Tanaka, Nobukatsu Hojo
2023	A	`conf`	Impact of Residual Noise and Artifacts in Speech Enhancement Errors on Intelligibility of Human and Machine. INTERSPEECH Shoko Araki, Ayako Yamamoto, Tsubasa Ochiai, Kenichi Arai, Atsunori Ogawa, Tomohiro Nakatani, Toshio Irino
2023	A	`conf`	Knowledge Distillation for Neural Transducer-based Target-Speaker ASR: Exploiting Parallel Mixture/Single-Talker Speech Data. INTERSPEECH Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takanori Ashihara, Kohei Matsuura, Tomohiro Tanaka, Ryo Masumura, Atsunori Ogawa, Taichi Asami
2023	J	`jnl`	Mask-Based Neural Beamforming for Moving Speakers With Self-Attention-Based Tracking. IEEE ACM Trans. Audio Speech Lang. Process. Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Shoko Araki
2023	J	`jnl`	Neural Target Speech Extraction: An Overview. CoRR Katerina Zmolíková, Marc Delcroix, Tsubasa Ochiai, Keisuke Kinoshita, Jan Cernocký, Dong Yu
2023	J	`jnl`	Neural Target Speech Extraction: An overview. IEEE Signal Process. Mag. Katerina Zmolíková, Marc Delcroix, Tsubasa Ochiai, Keisuke Kinoshita, Jan Cernocký, Dong Yu
2023	J	`jnl`	SoundBeam: Target Sound Extraction Conditioned on Sound-Class Labels and Enrollment Clues for Increased Performance and Continuous Learning. IEEE ACM Trans. Audio Speech Lang. Process. Marc Delcroix, Jorge Bennasar Vázquez, Tsubasa Ochiai, Keisuke Kinoshita, Yasunori Ohishi, Shoko Araki
2023	J	`jnl`	Streaming End-to-End Target-Speaker Automatic Speech Recognition and Activity Detection. IEEE Access Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takahiro Shinozaki
2022	—	`conf`	Analysis of Impact of Emotions on Target Speech Extraction and Speech Separation. IWAENC Jan Svec, Katerina Zmolíková, Martin Kocour, Marc Delcroix, Tsubasa Ochiai, Ladislav Mosner, Jan Honza Cernocký
2022	J	`jnl`	Analysis of impact of emotions on target speech extraction and speech separation. CoRR Jan Svec, Katerina Zmolíková, Martin Kocour, Marc Delcroix, Tsubasa Ochiai, Ladislav Mosner, Jan Cernocký
2022	A*	`conf`	ConceptBeam: Concept Driven Target Speech Extraction. ACM Multimedia Yasunori Ohishi, Marc Delcroix, Tsubasa Ochiai, Shoko Araki, Daiki Takeuchi, Daisuke Niizumi, Akisato Kimura, Noboru Harada, Kunio Kashino
2022	J	`jnl`	ConceptBeam: Concept Driven Target Speech Extraction. CoRR Yasunori Ohishi, Marc Delcroix, Tsubasa Ochiai, Shoko Araki, Daiki Takeuchi, Daisuke Niizumi, Akisato Kimura, Noboru Harada, Kunio Kashino
2022	J	`jnl`	How Bad Are Artifacts?: Analyzing the Impact of Speech Enhancement Errors on ASR. CoRR Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2022	A	`conf`	How bad are artifacts?: Analyzing the impact of speech enhancement errors on ASR. INTERSPEECH Kazuma Iwamoto, Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Hiroshi Sato, Shoko Araki, Shigeru Katagiri
2022	Misc	`conf`	Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition. ICASSP Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Naoyuki Kamo, Takafumi Moriya
2022	J	`jnl`	Learning to Enhance or Not: Neural Network-Based Switching of Enhanced and Observed Signals for Overlapping Speech Recognition. CoRR Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Naoyuki Kamo, Takafumi Moriya
2022	A	`conf`	Listen only to me! How well can target speech extraction handle false alarms? INTERSPEECH Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Katerina Zmolíková, Hiroshi Sato, Tomohiro Nakatani
2022	J	`jnl`	Listen only to me! How well can target speech extraction handle false alarms? CoRR Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Katerina Zmolíková, Hiroshi Sato, Tomohiro Nakatani
2022	J	`jnl`	Mask-based Neural Beamforming for Moving Speakers with Self-Attention-based Tracking. CoRR Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Shoko Araki
2022	A	`conf`	Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model. INTERSPEECH Martin Kocour, Katerina Zmolíková, Lucas Ondel, Jan Svec, Marc Delcroix, Tsubasa Ochiai, Lukás Burget, Jan Cernocký
2022	J	`jnl`	SoundBeam: Target sound extraction conditioned on sound-class labels and enrollment clues for increased performance and continuous learning. CoRR Marc Delcroix, Jorge Bennasar Vázquez, Tsubasa Ochiai, Keisuke Kinoshita, Yasunori Ohishi, Shoko Araki
2022	A	`conf`	Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations. INTERSPEECH Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Ryo Masumura
2022	J	`jnl`	Strategies to Improve Robustness of Target Speech Extraction to Enrollment Variations. CoRR Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoki Makishima, Mana Ihori, Tomohiro Tanaka, Ryo Masumura
2022	A	`conf`	Streaming Target-Speaker ASR with Neural Transducer. INTERSPEECH Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takahiro Shinozaki
2022	J	`jnl`	Streaming Target-Speaker ASR with Neural Transducer. CoRR Takafumi Moriya, Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Takahiro Shinozaki
2021	Misc	`conf`	Convolutive Transfer Function Invariant SDR Training Criteria for Multi-Channel Reverberant Speech Separation. ICASSP Christoph Böddeker, Wangyou Zhang, Tomohiro Nakatani, Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Naoyuki Kamo, Yanmin Qian, Reinhold Haeb-Umbach
2021	Misc	`conf`	Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain. ICASSP Julio Wissing, Benedikt T. Boenninghoff, Dorothea Kolossa, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Christopher Schymura
2021	J	`jnl`	Data Fusion for Audiovisual Speaker Localization: Extending Dynamic Stream Weights to the Spatial Domain. CoRR Julio Wissing, Benedikt T. Boenninghoff, Dorothea Kolossa, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Christopher Schymura
2021	Misc	`conf`	End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend. ICASSP Wangyou Zhang, Christoph Böddeker, Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Naoyuki Kamo, Reinhold Haeb-Umbach, Yanmin Qian
2021	J	`jnl`	End-to-End Dereverberation, Beamforming, and Speech Recognition with Improved Numerical Stability and Advanced Frontend. CoRR Wangyou Zhang, Christoph Böddeker, Shinji Watanabe, Tomohiro Nakatani, Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Naoyuki Kamo, Reinhold Haeb-Umbach, Yanmin Qian
2021	J	`jnl`	Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization. CoRR Christopher Schymura, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa
2021	A	`conf`	Few-Shot Learning of New Sound Classes for Target Sound Extraction. Interspeech Marc Delcroix, Jorge Bennasar Vázquez, Tsubasa Ochiai, Keisuke Kinoshita, Shoko Araki
2021	J	`jnl`	Few-shot learning of new sound classes for target sound extraction. CoRR Marc Delcroix, Jorge Bennasar Vázquez, Tsubasa Ochiai, Keisuke Kinoshita, Shoko Araki
2021	—	`conf`	Multimodal Attention Fusion for Target Speaker Extraction. SLT Hiroshi Sato, Tsubasa Ochiai, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Shoko Araki
2021	J	`jnl`	Multimodal Attention Fusion for Target Speaker Extraction. CoRR Hiroshi Sato, Tsubasa Ochiai, Keisuke Kinoshita, Marc Delcroix, Tomohiro Nakatani, Shoko Araki
2021	Misc	`conf`	Neural Network-Based Virtual Microphone Estimator. ICASSP Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki
2021	J	`jnl`	Neural Network-based Virtual Microphone Estimator. CoRR Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani, Rintaro Ikeshita, Keisuke Kinoshita, Shoko Araki
2021	A	`conf`	PILOT: Introducing Transformers for Probabilistic Sound Event Localization. Interspeech Christopher Schymura, Benedikt T. Bönninghoff, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa
2021	J	`jnl`	PILOT: Introducing Transformers for Probabilistic Sound Event Localization. CoRR Christopher Schymura, Benedikt T. Bönninghoff, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa
2021	J	`jnl`	Revisiting joint decoding based multi-talker speech recognition with DNN acoustic model. CoRR Martin Kocour, Katerina Zmolíková, Lucas Ondel, Jan Svec, Marc Delcroix, Tsubasa Ochiai, Lukás Burget, Jan Cernocký
2021	A	`conf`	Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition. Interspeech Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoyuki Kamo
2021	J	`jnl`	Should We Always Separate?: Switching Between Enhanced and Observed Signals for Overlapping Speech Recognition. CoRR Hiroshi Sato, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Takafumi Moriya, Naoyuki Kamo
2021	Misc	`conf`	Simpleflat: A Simple Whole-Network Pre-Training Approach for RNN Transducer-Based End-to-End Speech Recognition. ICASSP Takafumi Moriya, Takanori Ashihara, Tomohiro Tanaka, Tsubasa Ochiai, Hiroshi Sato, Atsushi Ando, Yusuke Ijima, Ryo Masumura, Yusuke Shinohara
2021	Misc	`conf`	Speaker Activity Driven Neural Speech Extraction. ICASSP Marc Delcroix, Katerina Zmolíková, Tsubasa Ochiai, Keisuke Kinoshita, Tomohiro Nakatani
2021	J	`jnl`	Speaker activity driven neural speech extraction. CoRR Marc Delcroix, Katerina Zmolíková, Tsubasa Ochiai, Keisuke Kinoshita, Tomohiro Nakatani
2021	A	`conf`	Streaming End-to-End Speech Recognition for Hybrid RNN-T/Attention Architecture. Interspeech Takafumi Moriya, Tomohiro Tanaka, Takanori Ashihara, Tsubasa Ochiai, Hiroshi Sato, Atsushi Ando, Ryo Masumura, Marc Delcroix, Taichi Asami
2020	Misc	`conf`	A Dynamic Stream Weight Backprop Kalman Filter for Audiovisual Speaker Tracking. ICASSP Christopher Schymura, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa
2020	Misc	`conf`	Beam-TasNet: Time-domain Audio Separation Network Meets Frequency-domain Beamformer. ICASSP Tsubasa Ochiai, Marc Delcroix, Rintaro Ikeshita, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki
2020	J	`jnl`	Convolutive Transfer Function Invariant SDR training criteria for Multi-Channel Reverberant Speech Separation. CoRR Christoph Böddeker, Wangyou Zhang, Tomohiro Nakatani, Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Naoyuki Kamo, Yanmin Qian, Shinji Watanabe, Reinhold Haeb-Umbach
2020	Misc	`conf`	DNN-supported Mask-based Convolutional Beamforming for Simultaneous Denoising, Dereverberation, and Source Separation. ICASSP Tomohiro Nakatani, Riki Takahashi, Tsubasa Ochiai, Keisuke Kinoshita, Rintaro Ikeshita, Marc Delcroix, Shoko Araki
2020	—	`conf`	Exploiting Attention-based Sequence-to-Sequence Architectures for Sound Event Localization. EUSIPCO Christopher Schymura, Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Tomohiro Nakatani, Shoko Araki, Dorothea Kolossa
2020	Misc	`conf`	Improving Noise Robust Automatic Speech Recognition with Single-Channel Time-Domain Enhancement Network. ICASSP Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani
2020	Misc	`conf`	Improving Speaker Discrimination of Target Speech Extraction With Time-Domain Speakerbeam. ICASSP Marc Delcroix, Tsubasa Ochiai, Katerina Zmolíková, Keisuke Kinoshita, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki
2020	J	`jnl`	Improving noise robust automatic speech recognition with single-channel time-domain enhancement network. CoRR Keisuke Kinoshita, Tsubasa Ochiai, Marc Delcroix, Tomohiro Nakatani
2020	J	`jnl`	Improving speaker discrimination of target speech extraction with time-domain SpeakerBeam. CoRR Marc Delcroix, Tsubasa Ochiai, Katerina Zmolíková, Keisuke Kinoshita, Naohiro Tawara, Tomohiro Nakatani, Shoko Araki
2020	A	`conf`	Listen to What You Want: Neural Network-Based Universal Sound Selector. INTERSPEECH Tsubasa Ochiai, Marc Delcroix, Yuma Koizumi, Hiroaki Ito, Keisuke Kinoshita, Shoko Araki
2020	J	`jnl`	Listen to What You Want: Neural Network-based Universal Sound Selector. CoRR Tsubasa Ochiai, Marc Delcroix, Yuma Koizumi, Hiroaki Ito, Keisuke Kinoshita, Shoko Araki
2020	A	`conf`	Self-Distillation for Improving CTC-Transformer-Based ASR Systems. INTERSPEECH Takafumi Moriya, Tsubasa Ochiai, Shigeki Karita, Hiroshi Sato, Tomohiro Tanaka, Takanori Ashihara, Ryo Masumura, Yusuke Shinohara, Marc Delcroix
2019	Misc	`conf`	A Unified Framework for Neural Speech Separation and Extraction. ICASSP Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Tomohiro Nakatani
2019	Misc	`conf`	Compact Network for Speakerbeam Target Speaker Extraction. ICASSP Marc Delcroix, Katerina Zmolíková, Tsubasa Ochiai, Keisuke Kinoshita, Shoko Araki, Tomohiro Nakatani
2019	A	`conf`	End-to-End SpeakerBeam for Single Channel Target Speech Recognition. INTERSPEECH Marc Delcroix, Shinji Watanabe, Tsubasa Ochiai, Keisuke Kinoshita, Shigeki Karita, Atsunori Ogawa, Tomohiro Nakatani
2019	A	`conf`	Multimodal SpeakerBeam: Single Channel Target Speech Extraction with Audio-Visual Speaker Clues. INTERSPEECH Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Tomohiro Nakatani
2019	J	`jnl`	SpeakerBeam: Speaker Aware Neural Network for Target Speaker Extraction in Speech Mixtures. IEEE J. Sel. Top. Signal Process. Katerina Zmolíková, Marc Delcroix, Keisuke Kinoshita, Tsubasa Ochiai, Tomohiro Nakatani, Lukás Burget, Jan Cernocký
2018	A	`conf`	ESPnet: End-to-End Speech Processing Toolkit. INTERSPEECH Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, Tsubasa Ochiai
2018	J	`jnl`	ESPnet: End-to-End Speech Processing Toolkit. CoRR Shinji Watanabe, Takaaki Hori, Shigeki Karita, Tomoki Hayashi, Jiro Nishitoba, Yuya Unno, Nelson Enrique Yalta Soplin, Jahn Heymann, Matthew Wiesner, Nanxin Chen, Adithya Renduchintala, Tsubasa Ochiai
2018	Misc	`conf`	Speaker Adaptation for Multichannel End-to-End Speech Recognition. ICASSP Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri, Takaaki Hori, John R. Hershey
2017	Misc	`conf`	Automatic node selection for Deep Neural Networks using Group Lasso regularization. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
2017	Misc	`conf`	Cumulative moving averaged bottleneck speaker vectors for online speaker adaptation of CNN-based acoustic models. ICASSP Tsubasa Ochiai, Marc Delcroix, Keisuke Kinoshita, Atsunori Ogawa, Taichi Asami, Shigeru Katagiri, Tomohiro Nakatani
2017	—	`conf`	Does speech enhancement work with end-to-end ASR objectives?: Experimental analysis of multichannel end-to-end ASR. MLSP Tsubasa Ochiai, Shinji Watanabe, Shigeru Katagiri
2017	A*	`conf`	Multichannel End-to-end Speech Recognition. ICML Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey
2017	J	`jnl`	Multichannel End-to-end Speech Recognition. CoRR Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey
2017	J	`jnl`	Unified Architecture for Multichannel End-to-End Speech Recognition With Neural Beamforming. IEEE J. Sel. Top. Signal Process. Tsubasa Ochiai, Shinji Watanabe, Takaaki Hori, John R. Hershey, Xiong Xiao
2016	J	`jnl`	Automatic Node Selection for Deep Neural Networks using Group Lasso Regularization. CoRR Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Shigeru Katagiri
2016	Misc	`conf`	Bottleneck linear transformation network adaptation for speaker adaptive training-based hybrid DNN-HMM speech recognizer. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Hisashi Kawai, Shigeru Katagiri
2016	J	`jnl`	Speaker Adaptive Training Localizing Speaker Modules in DNN for Hybrid DNN-HMM Speech Recognizers. IEICE Trans. Inf. Syst. Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Hisashi Kawai, Shigeru Katagiri
2015	Misc	`conf`	Speaker adaptive training for deep neural networks embedding linear transformation networks. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Hideyuki Watanabe, Xugang Lu, Chiori Hori, Shigeru Katagiri
2014	Misc	`conf`	Speaker Adaptive Training using Deep Neural Networks. ICASSP Tsubasa Ochiai, Shigeki Matsuda, Xugang Lu, Chiori Hori, Shigeru Katagiri